Pixel detection system and method

Abstract

Aspects of the subject technology provide improved pixel detection techniques, including motion detection improvements and processing resource savings. An improved technique includes determining a mutual information indicator between a pair of images of a series of images from a biological sample; detecting motion of the biological sample based on the mutual information indicator; and after detecting the motion, performing a biological sample measurement based on the test image of the image series.

Description

Technical Field

[0001] The present disclosure relates generally to image processing and biological classification and measurement. Background Art

[0002] Pixel detection techniques generally involve analyzing or measuring biological specimens based on digital (e.g., pixel-based) images of collected biological specimens. For example, a biological specimen can be mounted in a microscope capable of capturing digital images or videos, and the resulting digital images can be analyzed to classify or otherwise measure the biological specimen. However, existing techniques have certain drawbacks, such as relatively high CPU usage. Therefore, there is a need in the art for improved pixel detection techniques. Summary of the Invention

[0003] In meeting the long-standing unmet need, the present disclosure provides an image processing method, which includes determining a mutual information index between at least one pair of images in a series of images from a biological sample, detecting movement of the biological sample based on the mutual information index; and, after detecting the movement, performing biological sample measurement based on a test image of the image series.

[0004] An image processing method is also provided, the method comprising determining a mutual information index between at least one pair of images in a series of images from a biological sample; detecting movement of the biological sample based on the mutual information index; and after detecting the movement, performing biological sample measurement based on a test image of the image series.

[0005] Further provided is a non-transitory computer-readable memory storing instructions that, when executed by a processor, cause the processor to determine a mutual information index between at least one pair of images in a series of images from a biological sample; detect motion of the biological sample based on the mutual information index; and, after detecting the motion, perform a measurement of the biological sample based on a test image of the series of images. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Certain features of the subject technology are set forth in the appended claims. However, for illustrative purposes, several implementations of the subject technology are set forth in the following schematic, non-limiting drawings.

[0007] Figure 1 An exemplary image processing scenario is shown.

[0008] Figure 2 An exemplary image processing system in accordance with aspects of the subject technology is shown.

[0009] Figure 3 An exemplary pixel detection system in accordance with aspects of the subject technology is shown.

[0010] Figure 4An exemplary mutual information measurement system in accordance with aspects of the subject technology is shown.

[0011] Figure 5 Exemplary biometric methods in accordance with aspects of the subject technology are shown.

[0012] Figure 6 An exemplary computing system in accordance with aspects of the subject technology is shown. DETAILED DESCRIPTION

[0013] The detailed description of the invention set forth below is intended to serve as a description of various configurations of the subject technology and is not intended to represent the only configuration in which the subject technology can be implemented. The accompanying drawings are incorporated herein and constitute a part of the detailed description of the invention. The detailed description includes specific details intended to provide a thorough understanding of the subject technology. However, the subject technology is not limited to the specific details described herein and may be implemented using one or more other implementations. In one or more implementations, structures and components are shown in block diagram form to avoid obscuring the concept of the subject technology.

[0014] The present disclosure provides, among other things, improved pixel detection techniques. Conventional image processing techniques often do not work well with laboratory images of biological specimens, and therefore, techniques adapted for processing such images may produce improved results. In particular, transmitted light images (where the primary light source is located behind the specimen and the camera captures light that passes through the specimen rather than reflected from it) and images of radiated specimens (where the specimen generates and radiates electromagnetic energy, the latter captured by a camera independent of any other light sources) often do not work well with pixel detection techniques or other image processing techniques designed for reflected light images (where the primary light source is reflected from the specimen). Furthermore, specimens having substantial fluid components, or specimens immersed in a fluid medium, may interfere with conventional image processing techniques, or render them less efficient, particularly when captured in transmitted images.

[0015] In one aspect of the subject technology presented herein, mutual information can form the basis of improved techniques for identifying motion or other changes in biological specimens. For example, a mutual information metric between two sequential images of a given image object (e.g., a biological specimen) can be used to detect or measure motion or other changes in the object that occurred between the time the two images were acquired. Such motion can be, for example, cell expansion, cell contraction, or cell translational motion. Some examples of such other changes include, for example, an increase or decrease in the amount of a cellular component or cellular product, movement of a cellular component within a cell, cell replication, and the like. The mutual information metric can be based, for example, on a measure of statistical independence between the two images or between corresponding pixels in the two images. Experimental results have shown that the mutual information metric can provide improved detection or classification of motion or other changes in biological specimen images. For example, the mutual information metric can be relatively more sensitive to changes in biological specimens that are relevant to certain clinical applications (e.g., cell growth or movement) while being relatively less sensitive to other, less relevant changes (e.g., movement of the medium in which the biological specimen is immersed).

[0016] In another aspect of the disclosed technology, measurements of motion or other changes in an image subject (e.g., a biological specimen) can be used to improve the performance of a biological measurement. For example, when motion or other changes are detected in a biological specimen, a resource-intensive task can be initiated, such as performing a pixel detection method or any other resource-intensive biological measurement on a test image. In one aspect, when no changes are detected, resources (e.g., computer processor or memory usage) can be conserved by abandoning the resource-intensive task.

[0017] Improved pixel detection techniques may include determining a mutual information metric between at least one pair of images in a series of images from a biological sample; detecting motion of the biological sample based on the mutual information metric; and, after detecting motion, performing a biological sample measurement, such as a confluence metric, based on a test image from the image series. Such an image may, for example, be a transmitted light image. In the improved techniques, (i) the techniques may include forgoing performing a biological sample measurement when no motion is detected; (ii) determining the mutual information metric may include estimating a measure of statistical independence between co-located pixel values ​​in the image pair; (iii) estimating the measure of statistical independence may include determining a joint histogram of co-located pixel values; (iv) detecting motion when the mutual information metric exceeds a mutual information threshold level; (v) detecting motion based on multiple mutual information metrics, wherein each of the multiple metrics is between different image pairs from the image series; (vi) delaying performing a biological sample measurement after detecting motion until motion is no longer detected; and / or (vii) performing a biological sample measurement may include processing the test image with a machine learning model to generate a quantity value for the biological sample.

[0018] In yet another aspect of the improved technique, performing a biological sample measurement may include: analyzing a test image from an image series to generate a plurality of feature images; deriving a likelihood image for each of a plurality of object types from the feature images; and combining the likelihood images into a classification image, the classification image indicating which of the plurality of object types is detected at each pixel in the classification image. An exemplary biological measurement may include determining a confluence index, and the improved technique may include calculating the confluence index for the object type based on the percentage of pixels in the classification image indicating the object type.

[0019] Figure 1 An exemplary image processing scene 100 is shown. Scene 100 includes a specimen 102 comprising cells 112 in a specimen container 110, a camera 104 configured to capture images of specimen 102, a light source 114, an image processor 106, and a display 108. Light source 114 can emit visible light or other electromagnetic radiation, and can be positioned opposite camera 104 relative to specimen 102 such that emission from light source 114 is radiated in direction 116 to penetrate translucent or transparent portions of specimen 102 for ultimate capture by a light sensor in camera 104. Image processor 106 can process one or more images of specimen 102 captured by camera 104 to generate a biomass value for specimen 102, and can present the resulting value, such as a confluence metric, to a user on display 108. In one aspect, the value presented on display 108 is updated only when the image processor detects some type of change or movement in specimen 102. For example, if a user were to reposition specimen 102 relative to camera 104 so that camera 104 acquires an image of a different portion of specimen 102, the user may wish to immediately update the biomass value. At other times, such as when the operator has not moved specimen 102, image processor 106 may forgo updating the biomass value in order to conserve resources used by image processor 106 when it is unlikely that the biomass value has changed.

[0020] Figure 2 1 shows an exemplary image processing system 200 in accordance with aspects of the subject technology. The system 200 may be an image processor 106 ( Figure 1). System 200 includes a motion detector 202, a controller 204, and a pixel detector 206. In operation, an image source may provide a series of images acquired at different times. In one aspect, one or more images in the acquired series may contain the same image subject, for example, multiple images of the same biological sample. Motion detector 202 may assess motion or other changes occurring between a pair of images from the image source. In one aspect, the image pair may be adjacent or sequential images from the image source; in another aspect, the image pair may be temporally distant and represent a significant difference in image acquisition time. In one aspect, motion detector 202 may include a mutual information measurement module 208, and motion detector 208 may be capable of detecting motion based on the measured mutual information. For example, a mutual information metric may indicate the degree of motion occurring between the acquisition times of the image pair, and the mutual information metric may be normalized as described below. In another example, motion may be detected by a decrease in the mutual information metric below a threshold level. Pixel detector 206 may perform biometric measurements on the image subject in a test image from the image source. In one aspect, the test image used by pixel detector 206 can be one of the images in the pair used by motion detector 202, such as the most recent image in the pair. In another aspect, the test image used by pixel detector 206 can be different from the images in the pair used by motion detector 207, for example, the test image can be newer or more recent than either image in the pair. Controller 204 can control pixel detector 206 to perform a biometric measurement based on the motion detected by motion detector 202. For example, controller 204 can initiate a biometric measurement via pixel detector 206 only if the motion detector detects a certain amount of motion or nature of motion between the image pair.

[0021] In some aspects of system 200, pixel detector 206 may include one or more of the following: feature generator 210, likelihood generator 212, pixel classifier 213, convergence metric generator 214, and one or more machine learning models 216. In one aspect, the one or more machine learning models may analyze a test image to generate a magnitude of an object in the test image. In another aspect, feature generator 210, likelihood generator 212, pixel classifier 213, and convergence metric generator 214 may be used in combination to generate a magnitude of an object in the test image. In some implementations, feature generator 210, likelihood generator 212, pixel classifier 213, and / or convergence metric generator 214 may each independently include a machine learning model.

[0022] In another additional aspect, pixel detector 206 can generate a biomass value, such as confluence, for the specimen collected in the test image. For example, a confluence indicator for the specimen can be determined by confluence generator 214 from the output of pixel classifier 214. The confluence indicator can be determined as a ratio of the number of pixels having different classifications generated by the pixel classifier for the image. For example, the confluence indicator can be determined as the ratio of the number of pixels in the test image classified as a certain cell type to the total number of pixels in the test image.

[0023] Figure 3 2. An exemplary pixel detection system 300 according to aspects of the subject technology is shown. The pixel detection system 300 may be a pixel detector 206 ( Figure 2 ). System 300 includes a feature generator 302, a likelihood generator 304, and a pixel classifier 306. During operation, feature generator 302 can generate at least one or more feature images 312 from a test image 310. The likelihood generator can generate one or more likelihood images 314 from the feature images 312. The pixel classifier 306 can generate a classification image 316 based on the likelihood images 314.

[0024] The test image 310 may be, for example, a video from a camera 104 ( Figure 1 ), and can be, for example, a color image with multiple color component values ​​per pixel, or a grayscale image with a single color (grayscale) component per pixel. Feature images 312 can indicate the locations of features of test image 310, where the pixel values ​​in the feature image indicate the presence of a feature type at that pixel location. Each feature image 312 generated from a single test image 310 can correspond to a different feature type, such as a computer vision feature (e.g., edge, texture, motion, etc.) or a statistical feature (e.g., a spatially localized mean or standard deviation of pixel intensity values), and have different localizations. Feature images with different localizations can characterize feature types using different localization techniques, such as by varying the size of a window around an output pixel (e.g., varying the radius from the output pixel), within which the source pixel is considered local. For example, feature detector 302 can generate six feature images 312 from a single test image 310, including three average images with localization radii of 2, 3, and 4 pixels, and two standard deviation images with localization radii of 2 and 5 pixels.

[0025] In various aspects, the feature generator 302 may apply a convolution filter to the test image 310 to generate a feature image 312 having the following features: Gaussian-weighted intensity features within local windows of various sizes to identify features at different scales; Gaussian-weighted local variance features with various window sizes; and / or Gabor filters for identifying image patterns or texture features.

[0026] The likelihood images 314 can each indicate the likelihood of a corresponding object type being present in the image objects of the test image 310. For example, the value of each pixel in the likelihood image can indicate an estimated probability that an object type (e.g., a particular organelle) is present at the corresponding location of each pixel within the test image 310. In aspects, one or more feature images 312 can be used by the likelihood generator to generate each likelihood image 314.

[0027] In one example, the likelihood generator 304 may generate a likelihood image for a specific classification class using the adjustable pseudo sensitivity parameter s by calculating the pixel-by-pixel probability as: in s = sensitivity, p class = the probability that a pixel belongs to a classification class, and p bkg = the maximum value of the probability that a certain pixel belongs to any background class (e.g., any class other than class ). The probability that a pixel belongs to a class can be determined based on a multivariate statistical distribution model generated from manually annotated training images. This model can model each class as a normal distribution using the full covariance matrix. The training images may contain manual annotations that distinguish between background and foreground pixel classes, or between background and cell edge pixels and cell center pixels.

[0028] In one aspect, the improved pixel detection techniques may include techniques for faster and / or more efficient processing. For example, during the generation of the classification image 316, the pixel detection techniques may be improved by processing a multivariate statistical model using single instruction multiple data (SIMD) parallelism. class Parallelize calculations to improve performance.

[0029] The pixel classifier 306 can combine the likelihood images 314 into a classification image 316 to indicate whether any object type is detected at the corresponding pixel of the test image 310. For example, the pixel classifier 306 can select which object type is most likely to be present at each pixel location. Alternatively, the pixel classifier 306 can indicate a count of objects detected at each pixel; or each pixel can indicate which object combination is detected at each pixel (e.g., using different colors to indicate the presence of different object types). In some embodiments, the pixel classifier can use a likelihood threshold to determine whether a certain object type is present at a certain pixel location.

[0030] Figure 4 An exemplary mutual information measurement system 400 according to aspects of the subject technology is shown. The system 400 may be a mutual information measurement unit 208 ( Figure 2 ). System 400 includes a statistical data collection unit 404, an entropy estimation unit 406, and a mutual information index calculation unit 408. In operation, statistical data collection unit 404 may collect statistical data of pixel data in image pair 402. Entropy estimation unit 406 may estimate the entropy of image pair 402 based on the statistical data collected by statistical data collection unit 404. Mutual information index calculation unit 408 may calculate the mutual information index of image pair 402 based on the entropy estimated by entropy estimation unit 406.

[0031] In an optional aspect of the system 400, the statistics collection unit 404 can include an edge histogram unit 410 and a joint histogram unit 412. The entropy estimation unit 406 can include an edge entropy unit 414 and a joint entropy unit 416. In one aspect, the edge entropy estimation in block 414 can be based on the edge histogram from block 410, while the joint entropy estimation in block 416 can be based on the joint histogram from block 412. In one aspect, the joint histogram for the image pair 402 can count the frequency of co-located pixel values ​​in the two images. For example, each entry in the joint histogram can indicate a count of pixels in the image pair for which one image of the image pair has a first pixel value and a corresponding co-located pixel in the other image has a second pixel value.

[0032] In some implementations, the mutual information metric between the two images can be normalized based on a separate estimate of the entropy of each of the two images. For example, the normalized mutual information I norm It can be calculated as where I(X;Y) is the mutual information between images X and Y, and H(X) is the individual entropy of image X.

[0033] Figure 5 An exemplary biometric method 500 according to aspects of the subject technology is shown. The method 500 may be performed by the image processor 106 ( Figure 1 ) or System 200( Figure 2 ). The method 500 includes: calculating a mutual information metric from a pair of images (506); detecting motion based on the calculated mutual information metric (508); and performing biometric measurement on an image object in a test image (Figure 512).

[0034] The mutual information metric may be based on Shannon's definition of entropy H and mutual information I(X; Y). In the operation of the exemplary implementation, the mutual information metric (506) may be based on the mutual information measurement system 400 ( Figure 4) as described above. In one aspect, statistics for the image pair may be collected (block 504), as described above with respect to Figure 4 As described, these statistics may be based on a selected bin size for the histogram (502).

[0035] For example, motion may be detected (508) when the mutual information indicator drops below a threshold level indicating that one image in a pair of images is not well predicted by the other image in the pair. In one aspect, execution of the biometric measurement (512) may be delayed (510) for a period of time after the initial detection of motion (508). For example, after the initial detection of motion, the biometric measurement (512) may not be initiated until motion is no longer detected. In one aspect, a first threshold value of the mutual information indicator may be used to detect when motion begins, and a second threshold value of the mutual information indicator may be used to detect when motion stops. Alternatively or additionally, a fixed or variable time delay may be added before initiating the biometric measurement. For example, the biometric measurement may be initiated 3 seconds after the initial detection of motion, or 2 seconds after motion is no longer detected.

[0036] In operation, performing biometrics (512) may optionally include classifying pixels (514) and calculating a convergence level (516) based on the pixel classifications.

[0037] Figure 6 An example computing device 600 is shown, with which aspects of the subject technology, including but not limited to systems 200, 300, 400 ( Figure 2-4 ) and method 500( Figure 5 ). The computing device 600 can be any computing device or server used to generate the above-mentioned features and processes and / or can be part thereof, including but not limited to a laptop computer, a smart phone, a tablet device, a wearable device such as goggles or glasses, earbuds or other audio devices, and an audio device housing. The computing device 600 can include various types of computer-readable media and interfaces for various other types of computer-readable media. The computing device 600 includes a permanent storage device 602, a system memory 604 (and / or cache), an input device interface 606, an output device interface 608, a bus 610, a read-only memory (ROM) 612, one or more processing units 614, one or more network interfaces 616, and / or subsets and variations thereof.

[0038] Bus 610 collectively represents the system bus, peripheral bus, and chipset bus that communicatively connect the numerous internal devices of computing device 600. In one or more embodiments, bus 610 communicatively connects one or more processing units 614 to ROM 612, system memory 604, and permanent storage. From these various memory units, one or more processing units 614 retrieve instructions to execute and data to process to perform the processes of the present disclosure. In various implementations, one or more processing units 614 may be single-core processors or multi-core processors.

[0039] ROM 612 stores static data and instructions required by one or more processing units 614 and other modules of computing device 600. On the other hand, permanent storage 602 can be a read-write memory device. Persistent storage 602 can be a non-volatile memory unit that stores instructions and data even when computing device 600 is turned off. In one or more implementations, a mass storage device (such as a magnetic or optical disk and its corresponding disk drive) can be used as permanent storage 602.

[0040] In one or more implementations, a removable storage device (e.g., a floppy disk, a flash drive, and its corresponding disk drive) can be used as the permanent storage device 602. Like the permanent storage device 602, the permanent storage device 604 can be a read-write storage device. However, unlike the permanent storage device 602, the system memory 604 can be a volatile read-write memory, such as random access memory. The system memory 604 can store any instructions and data that one or more processing units 614 may need during execution. In one or more implementations, the processes disclosed herein are stored in the system memory 604, the permanent storage device 602, and / or the read-only memory 612. From these various storage units, the one or more processing units 614 retrieve instructions to be executed and data to be processed to execute the processes of one or more implementations.

[0041] The bus 610 is also connected to an input device interface 606 and an output device interface 608. The input device interface 606 enables a user to transmit information and select commands to the computing device 600. Input devices that can be used with the input device interface 606 can include, but are not limited to, an alphanumeric keyboard and a pointing device (also referred to as a "cursor control device"). The output device interface 608 can, for example, be capable of displaying images generated by the computing device 600. Output devices that can be used with the output device interface 608 can include, but are not limited to, a printer and a display device, such as a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a flexible display, a flat panel display, a solid-state display, a projector, or any other device for outputting information.

[0042] One or more implementations may include a device that functions as both an input and output device, such as a touch screen. In these implementations, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and the input from the user may be received in any form, including sound input, voice input, or tactile input.

[0043] Finally, if Figure 6 As shown in FIG, bus 610 also couples computing device 600 to one or more networks and / or one or more network nodes via one or more network interfaces 616. Thus, computing device 600 can be part of a computer network, such as a local area network ("LAN"), a wide area network ("WAN"), an intranet, or a network of networks, such as the Internet. Any or all components of computing device 600 can be used in conjunction with the subject disclosure.

[0044] Implementations within the scope of the present disclosure may be implemented in part or in whole using a tangible computer-readable storage medium (or one or more types of one or more tangible computer-readable storage media) encoding one or more instructions. Tangible computer-readable storage media may also be non-transitory in nature.

[0045] Computer-readable storage media can be any storage medium that can be read, written, or otherwise accessed by a general-purpose or special-purpose computing device, including any processing electronics and / or processing circuitry capable of executing instructions. For example, but not limited to, computer-readable media can include any volatile semiconductor memory, such as RAM, DRAM, SRAM, T-RAM, Z-RAM, and TTRAM. Computer-readable media can also include any non-volatile conductive memory, such as ROM, PROM, EPROM, EEPROM, NVRAM, flash memory, nvSRAM, FeRAM, FeTRAM, MRAM, PRAM, CBRAM, SONOS, RRAM, NRAM, racetrack memory, FJG, and millipede memory.

[0046] Furthermore, the computer-readable storage medium may include any non-semiconductor memory, such as optical disk storage, magnetic disk storage, magnetic tape, other magnetic storage devices, or any other medium capable of storing one or more instructions. In one or more implementations, the tangible computer-readable storage medium may be directly coupled to the computing device; while in other implementations, the tangible computer-readable storage medium may be indirectly coupled to the computing device, for example, via one or more wired connections, one or more wireless connections, or any combination thereof.

[0047] Instructions can be directly executable or can be used to develop executable instructions. For example, instructions can be implemented as executable or non-executable machine code, or can be implemented as high-level language instructions that can be compiled to produce executable or non-executable machine code. In addition, instructions can also be implemented as data or can include data. Computer-executable instructions can be organized in any form, including routines, subroutines, programs, data structures, objects, modules, applications, applets, functions, etc. As will be appreciated by those skilled in the art, details, including but not limited to the number, structure, order, and organization of instructions, may vary significantly without changing the underlying logic, functionality, processing, and output.

[0048] While the above discussion primarily refers to microprocessors or multi-core processors executing software, one or more implementations are performed using one or more integrated circuits, such as application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs). In one or more implementations, such integrated circuits execute instructions stored within their circuitry.

[0049] Those skilled in the art will appreciate that the various illustrative functional blocks, modules, elements, components, methods, and algorithms described herein can be implemented as electronic hardware, computer software, or a combination thereof. In order to illustrate the interchangeability of hardware and software, various illustrative functional blocks, modules, elements, components, methods, and algorithms have been generally described above with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the entire system. A skilled person can implement the described functionality in different ways for each specific application. The various components and functional blocks can be configured in different ways (e.g., arranged in different orders, or divided in different ways) without departing from the scope of the present subject technology.

[0050] It will be understood that any specific order or hierarchical relationship of the modules in the disclosed process is an illustration of an exemplary method. Depending on design preferences, it will be understood that the specific order or hierarchical relationship of the functional blocks in the process can be reconfigured, or all of the functional blocks shown can be executed. Any of the functional blocks can be executed synchronously. In one or more implementations, multitasking and parallel processing may be advantageous. In addition, the separation of various system components in the implementations described above should not be understood as requiring such separation in all implementations, but it should be understood that the described program components (e.g., computer program products) and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0051] As used in this specification and any claims of this application, the terms "base station," "receiver," "computer," "server," "processor," and "memory" refer to electronic devices or other technical equipment. These terms do not include people or groups of people. For the purposes of this specification, the terms "display" or "displaying" mean displaying on an electronic device.

[0052] Within the scope of this document, the phrase "at least one of" preceding a series of items, together with the terms "and" or "or" separating any of those items, modifies the series as a whole, rather than each member (i.e., each item) of the series. The phrase "at least one of" does not require selection of at least one of each listed item; rather, the phrase allows for a meaning that includes at least one of any of those items, and / or at least one of any combination of those items, and / or at least one of each of those items. For example, the phrase "at least one of A, B, and C" or "at least one of A, B, or C" each refers to only A, only B, or only C; any combination of A, B, and C; and / or at least one of each of A, B, and C.

[0053] The predicates "configured to," "operable to," and "programmed to" do not imply any specific tangible or intangible modification of the subject matter, but are intended to be used interchangeably. In one or more implementations, a processor configured to monitor and control a certain operation or component may also mean that the processor is programmed to monitor and control the operation, or that the processor is operable to monitor and control the operation. Similarly, a processor configured to execute code may be interpreted as a processor that is programmed to execute code or operable to execute code.

[0054] Phrases such as "an aspect," "the aspect," "another aspect," "some aspects," "one or more aspects," "an implementation," "the implementation," "another implementation," "some implementations," "one or more implementations," "one embodiment," "the embodiment," "another embodiment," "some embodiments," "one or more embodiments," "a configuration," "the configuration," "another configuration," "some configurations," "one or more configurations," "the subject technology," "the present disclosure," "the present disclosure," and variations and the like are for convenience only and do not imply that the disclosure associated with such phrases is essential to the subject technology or that such disclosure applies to all configurations of the subject technology. The disclosure associated with such phrase(s) may apply to all configurations, or one or more configurations. The disclosure associated with such phrase(s) may provide one or more examples. Phrases such as an aspect or some aspects may refer to one or more aspects, and vice versa, and similarly apply to the other aforementioned phrases.

[0055] The word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any implementation described herein as "exemplary" or "example" is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, to the extent the description or claims use the terms "include," "have," or similar, such terms are intended to be inclusive in a manner similar to the term "comprise," as if "comprise" were interpreted when used as a transitional term in a claim.

[0056] All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to one of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public regardless of whether the claims expressly reference the disclosure. Unless a claim element is expressly recited by the phrase “means for,” or, in the case of a method claim, by the phrase “step for,” no claim element shall be construed under 35 U.S.C. § 112(f). ”

[0057] The foregoing description is provided to enable those skilled in the art to implement the various aspects described herein. Various modifications to these technical embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects a shown herein, but should be given a full scope consistent with the claim language, wherein reference to a singular element is not intended to mean "one and only one", unless specifically stated so, but rather means "one or more". Unless expressly stated otherwise, the term "some" should be understood to mean "one or more". Masculine pronouns (such as his) include feminine and neuter (such as her and its), and vice versa. Titles and subtitles (if any) are used for convenience only and do not limit subject disclosure.

Claims

1. An image processing method, comprising: determining a mutual information index between at least one pair of images in a series of images from a biological sample; Detecting the motion of biological samples based on mutual information metrics; and After the motion is detected, a measurement of the biological sample is performed based on the test images of the image series.

2. The image processing method according to claim 1, further comprising: When no motion is detected, the biological sample measurement is abandoned. 3 . The image processing method according to claim 1 , wherein determining the mutual information indicator comprises estimating a measure of statistical independence between co-located pixel values ​​in an image pair.

4. An image processing method according to claim 3, wherein estimating the measure of statistical independence includes determining a joint histogram of co-located pixel values. The image processing method according to claim 1 , wherein motion is detected when the mutual information indicator exceeds a mutual information threshold level. 6 . The image processing method according to claim 1 , wherein the motion is detected based on a plurality of mutual information indicators between different image pairs, each of the plurality of indicators being from an image series. 7 . The image processing method according to claim 1 , wherein after the motion is detected, the biological sample measurement is delayed until the motion is no longer detected.

8. The image processing method according to claim 1, wherein performing biological sample measurement comprises: The test images are processed with a machine learning model to produce magnitude values ​​for the biological samples.

9. The image processing method according to claim 1, wherein performing biological sample measurement comprises: analyzing a test image from the image series to generate a plurality of feature images; deriving a likelihood image for each of a plurality of object types from the feature image; as well as The likelihood images are combined into a classification image that indicates which of the plurality of object types is detected at each pixel in the classification image.

10. The method according to claim 9, further comprising: Based on the percentage of pixels in the classified image that indicate the object type, a convergence index for the object type is calculated.

11. The image processing method according to claim 9, wherein the plurality of feature images include an average image and a standard deviation image, wherein the average image has pixel values ​​each based on the mean of a pixel neighborhood in a test image, and the standard deviation image has pixel values ​​each based on the standard deviation of a pixel neighborhood in a test image. 12 . The image processing method according to claim 1 , wherein the image series of the biological sample is a transmitted light image series acquired by a camera under backlighting of the biological sample.

13. An image processing device comprising a controller configured to execute the method of claims 1-12.

14. A non-transitory computer-readable memory storing instructions, wherein when the instructions are executed by a processor, the processor is caused to perform the method according to claims 1-12.

Images